Speech enhancement method and apparatus for same
AssigneeSamsung Electronics Co., Ltd.
InventorsJae-youn Cho, Weiwei Cui, Seung-yeol Lee
Life of this patent
Estimating the term…
Abstract
A speech enhancement method is provided. The speech enhancement method includes: estimating a direction of a speaker by using an input signal, generating direction information indicating the estimated direction, detecting speech of a speaker based on a result of the estimating the direction, and enhancing the speech of the speaker by using the direction information based on a result of the detecting the speech.
Claims22
An electronic device comprising:
- a plurality of microphones;
- a processor configured to:
- detect, from at least one of the plurality of microphones, a signal associated with a speech of a speaker for initiating direction estimation of the speaker;
- based on the signal associated with the speech of the speaker being detected:
- estimate a direction of the speaker, based on a plurality of signals received from at least two of the plurality of microphones;
- and
- beamform the received plurality of signals such that at least one of the plurality of signals from the estimated direction is emphasized and at least another one of the plurality of signals is suppressed;
- and
- output the plurality of beamformed signals to perform speech recognition based on the plurality of beamformed signals.
(canceled)
A speech enhancement method being performed by an electronic device, the speech enhancement method comprising:
- detecting a signal associated with a speech of a speaker for initiating direction estimation of the speaker, from at least one of a plurality of microphones;
- based on the signal associated with the speech of the speaker being detected:
- estimating a direction of the speaker, based on a plurality of signals received from at least two of the plurality of microphones;
- and
- beamforming the received plurality of signals such that at least one of the plurality of signals from the estimated direction is emphasized and at least another one of the plurality of signals is suppressed;
- and
- outputting the plurality of beamformed signals to perform speech recognition based on the plurality of beamformed signals.
(canceled)
A non-transitory computer-readable storage medium storing instructions that cause a processor of an electronic device to:
- detect a signal associated with a speech of a speaker for initiating direction estimation of the speaker, from at least one of a plurality of microphones;
- based on the signal associated with the speech of the speaker being detected:
- estimate a direction of the speaker, based on a plurality of signals received from at least two of the plurality of microphones;
- and
- beamform the received plurality of signals such that at least one of the plurality of signals from the estimated direction is emphasized and at least another one of the plurality if signals is suppressed;
- and
- output the plurality of beamformed signals to perform speech recognition based on the plurality of beamformed signals.
A speech enhancement method being performed by an electronic device, the speech enhancement method comprising:
- controlling to detect a signal associated with a speech of a speaker for initiating direction estimation of the speaker, from at least one of a plurality of microphones;
- based on the signal associated with the speech of the speaker being detected:
- controlling to estimate a direction of the speaker based on a plurality of signals received from at least two of the plurality of microphones;
- and
- controlling to beamform the received plurality of signals such that at least one of the plurality of signals from the estimated direction is emphasized and at least another one of the plurality of signals is suppressed;
- and
- controlling to output the plurality of beamformed signals to perform speech recognition based on the plurality of beamformed signals.
Dependencies are inferred from the claim text.